CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

agent-workflow-designer

Design production-grade multi-agent workflows with clear pattern choice (sequential, parallel, hierarchical), handoff contracts, failure handling, and cost/context controls. Use when architecting a multi-step agent pipeline, choosing between single-agent vs multi-agent approaches, or refactoring an LLM workflow that suffers from context bloat or unreliable handoffs.

62

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.gemini/skills/agent-workflow-designer/SKILL.md

The canonical home for this skill is agent-workflow-designer in alirezarezvani/claude-skills

SKILL.md
Quality
Evals
Security

Quality

Content

63%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-organized, appropriately terse body with a sensible step sequence and useful pitfalls/best-practices sections. Its main weakness is that every path for going deeper (the scaffolder script and the pattern-templates reference) is dangling — none of the referenced bundle files are present — and the handoff-contract guidance stays abstract where an example schema would make it executable.

Suggestions

Ship the referenced bundle files (scripts/workflow_scaffolder.py and references/workflow-patterns.md), or remove/repair the Quick Start commands and the 'Detailed templates' pointer so no path dead-ends.

Add a minimal handoff contract example (field names plus a one-line JSON payload) under 'Recommended Workflow' so 'Define handoff contract fields for every edge' is executable rather than abstract.

Close the workflow loop by stating what to do when dry-run or output validation fails (e.g., tighten budgets, inspect the failing edge, re-validate), turning the sequence into an explicit validate-fix-retry cycle.

DimensionReasoningScore

Conciseness

Largely lean — no re-explanation of concepts Claude already knows, and bullets are tight. Minor trimming possible: the Overview repeats the frontmatter description verbatim, and 'Core Capabilities' substantially overlaps 'When to Use' and 'Recommended Workflow'.

4 / 5

Actionability

Quick Start gives concrete, syntax-complete commands ('python3 scripts/workflow_scaffolder.py sequential --name content-pipeline') but neither that script nor any scripts/ or references/ directory exists in the bundle, so the commands cannot run as shipped. Beyond scaffolding, key guidance stays abstract — 'Define handoff contract fields for every edge' and 'Dry-run with small context budgets' give no example contract fields or budget mechanism, falling between the 'minor gaps' (4) and 'pseudocode/incomplete' (3) anchors; the dangling script tips it to 3.

3 / 5

Workflow Clarity

'Recommended Workflow' presents a clear 5-step sequence (select pattern, scaffold, define contracts, add retry/validation, dry-run) with a validation gate ('Dry-run with small context budgets before scaling') and a matching 'Validate intermediate outputs before fan-in synthesis' best practice. Not a 5: there is no explicit feedback loop describing what to do when validation or the dry run fails.

4 / 5

Progressive Disclosure

The body is well-sectioned and the pointer 'Detailed templates: references/workflow-patterns.md' is clearly signaled and only one level deep — good 4-level structure on paper. However, the referenced file does not exist in the bundle (no references/ or scripts/ directories at all), so navigation dead-ends and the promised detail is unavailable; scoring against the actual bundle structure drops it to 3.

3 / 5

Total

14

/

20

Passed

Description

83%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description that explicitly states what the skill does and when to use it, with natural trigger phrases covering design, pattern choice, and refactoring scenarios. The only deductions are mild buzzword padding ('production-grade') and a few missing synonyms for the multi-agent domain.

DimensionReasoningScore

Specificity

Lists several concrete actions — 'pattern choice (sequential, parallel, hierarchical)', 'handoff contracts, failure handling, and cost/context controls' — with named pattern examples. Not a 5: 'production-grade' is buzzword padding and the action list has minor gaps (e.g., scaffolding/config generation mentioned only in the body).

4 / 5

Completeness

Clearly answers both halves: the 'what' is 'Design production-grade multi-agent workflows with clear pattern choice... handoff contracts, failure handling, and cost/context controls', followed by an explicit 'Use when...' with three concrete trigger conditions (architecting a pipeline, choosing single- vs multi-agent, refactoring a workflow with context bloat or unreliable handoffs).

5 / 5

Trigger Term Quality

Natural phrases users would actually say are present: 'multi-agent workflows', 'multi-step agent pipeline', 'single-agent vs multi-agent', 'context bloat', 'unreliable handoffs'. A few common variants are missing (e.g., 'subagents', 'orchestration', 'agent team'), keeping it below comprehensive synonym-level coverage.

4 / 5

Distinctiveness Conflict Risk

A clear niche (multi-agent workflow architecture) with triggers like 'context bloat' and 'unreliable handoffs' that other skills would not claim. Minor overlap risk with generic coding-architecture or orchestration skills, so not a fully isolated 5.

4 / 5

Total

17

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

referenced_paths_exist

Referenced path issues: 4 missing

Warning

Total

15

/

16

Passed

Repository

alirezarezvani/claude-skills

Path

.gemini/skills/agent-workflow-designer/SKILL.md

Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.